Method and system for judging applicable conditions of cage type anti-floating anchor rod

Abstract

The invention relates to the field of civil construction, and discloses a cage type anti-floating anchor application condition judgment method and system, and the method comprises the following steps: collecting field geological data; on-site geological data are learned based on a support vector machine algorithm, and a geological characteristic recognition model is established; according to the geological characteristic identification model, carrying out applicability evaluation on the field geological data, and outputting an anchor rod application suggestion; pre-estimating anchor rod design parameters according to the field geological data and the anchor rod application suggestions by using a deep neural network; and optimizing the anchor rod design parameters by adopting a genetic algorithm to obtain a design scheme. According to the method, the adaptability of the anchor rod in a complex geological environment can be recognized through a geological characteristic recognition model of the support vector machine, compared with a traditional geomechanical model, the defects caused by material heterogeneity and underground water flow field simplification are overcome, prediction precision limitation is avoided, the design misjudgment rate is remarkably reduced through more accurate geological recognition, and the method is suitable for popularization and application. And the scientificity and reliability of the design are improved.

Description

Technical Field

[0001] The present invention relates to the field of civil engineering construction, and specifically to a method and system for determining the applicable conditions of cage-type anti-floating anchor rods. Background Art

[0002] In a complex geological environment, ensuring the stability of structures such as foundation pits and bridge piers is crucial. Traditional geomechanical models play a key role in this process. They predict the bearing capacity and stability of anchor rods by calculating factors such as soil pressure distribution and hydrodynamic effects. These models have played an important role in promoting the safety and economy of structural design. Solutions of the prior art corresponding to the present technical solution: Traditional geomechanical models mainly include the finite element method and the boundary element method. These methods establish mathematical models based on the physical and mechanical property parameters of rock and soil masses, and simulate and predict the stress conditions and deformation modes of anchor rods.

[0003] However, such models often rely on idealized assumptions, such as ignoring the heterogeneity and anisotropy of materials and simplifying complex underground water flow fields, resulting in limited prediction accuracy. Especially in extremely complex geological conditions, large errors may occur, thus affecting the safety and reliability of engineering design. Summary of the Invention

[0004] In view of the deficiencies of the prior art, the present invention provides a method and system for determining the applicable conditions of cage-type anti-floating anchor rods, which solves the problem that the model is based on idealized assumptions, resulting in limited prediction accuracy and large errors in complex working conditions, thus affecting the safety and reliability of engineering design.

[0005] To achieve the above objectives, the present invention is realized through the following technical solutions: A method for determining the applicable conditions of cage-type anti-floating anchor rods includes the following steps: Collect on-site geological data; Based on the support vector machine algorithm, learn the on-site geological data to establish a geological characteristic recognition model; According to the geological characteristic recognition model, evaluate the applicability of the on-site geological data and output anchor rod application suggestions; Using a deep neural network, estimate the anchor rod design parameters based on the on-site geological data and anchor rod application suggestions; Optimize the anchor rod design parameters using a genetic algorithm to obtain a design scheme.

[0006] Preferably, the on-site geological data includes rock density, permeability coefficient, water content, and soil particle size distribution.

[0007] Preferably, the deep neural network includes an input layer, a hidden layer, and an output layer. The input layer is used to receive on-site geological data, and the output layer is used to estimate the anchor rod design parameters.

[0008] Preferably, the bolt design parameters include the length, diameter, and spacing of the bolt.

[0009] Preferably, based on the bolt design parameters, the genetic algorithm optimizes the bolt design parameters by simulating the process of natural evolution.

[0010] Preferably, the process of natural evolution includes: Selection: Select the design parameters with high fitness values as the parent generation; Crossover: Combine the parent design parameters through crossover to form new offspring design parameters, generating several design candidate solutions; Mutation: Mutate several design candidate solutions of the offspring, and the mutation includes randomly changing the design parameters; Evaluation: Calculate the fitness values of all design candidate solutions after mutation, and determine whether the design candidate solutions meet the design objectives according to the fitness values; Termination condition: When the design candidate solution meets the requirements, terminate the evolution process and output the design candidate solution as the optimal design solution.

[0011] Preferably, the deep neural network further includes probabilistic risk assessment for generating a risk assessment report based on seismic loads, groundwater level fluctuations, and seasonal temperature changes.

[0012] A determination system for the applicable conditions of a cage-type anti-floating bolt, comprising: A data acquisition module for collecting on-site geological data; A geological characteristic identification module that classifies the on-site geological data based on the support vector machine algorithm and outputs bolt application suggestions; a design parameter optimization module that combines a deep neural network and a genetic algorithm to optimize the bolt design parameters in the bolt application suggestions; a risk assessment module that generates a risk probability map and adjusts the design redundancy using a probabilistic risk assessment method based on the bolt design parameters optimized by the design parameter optimization module; A user interaction module for providing an interaction interface and real-time displaying the design solution and bolt design parameters.

[0013] The present invention provides a method and a system for determining the applicable conditions of a cage-type anti-floating bolt. The following beneficial effects are achieved: 1. By adopting an intelligent geological characteristic identification model based on the support vector machine algorithm, the present invention can accurately identify the adaptability of bolts in complex geological environments. Compared with traditional geomechanical models, this technology overcomes the deficiencies of ignoring material inhomogeneity and simplifying the groundwater flow field, avoiding the problem of limited prediction accuracy. Through more accurate geological characteristic identification, the misjudgment rate in the engineering design stage is significantly reduced, and the scientificity and reliability of the design solution are improved.

[0014] 2. By automating the optimization of design parameters using an integrated deep neural network and genetic algorithm, the present invention can significantly shorten the design cycle, improve work efficiency, and reduce human and time inputs. In addition, the automated optimization effectively reduces material waste, lowers project costs, and enhances overall economic benefits.

[0015] 3. By using a probabilistic risk assessment mechanism to analyze uncertain factors during the design process, including seismic loads and groundwater level fluctuations, generating a risk probability map, and adjusting design redundancy, the present technology significantly enhances the safety redundancy of the design scheme compared to existing solutions lacking comprehensive risk assessment. Even under extreme working conditions, the design scheme can ensure the stability of the anchor bolts, reduce potential risk hazards, and guarantee the safety and long-term feasibility of the engineering project. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 is a schematic flow chart of the method of the present invention; Figure 2 is a schematic diagram of the system architecture of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0017] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the specification of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0018] To better understand the present invention, the above content will be described in detail below with specific embodiments.

[0019] Example 1: Refer to the attached Figure 1 , the embodiment of the present invention provides a method for determining the applicable conditions of cage-type anti-floating anchor bolts, including the following steps: Collect on-site geological data; In this embodiment, the quality of the obtained geological data directly affects the subsequent identification of geological characteristics, estimation of anchor bolt design parameters, and the accuracy of the optimization results. Therefore, in the data collection stage, the present invention comprehensively considers the key parameters under different geological environments to ensure the comprehensiveness and representativeness of the geological data, providing a reliable input basis for subsequent calculations.

[0020] The collection of geological data mainly includes but is not limited to the following types of parameters: Generally, the rock density, permeability coefficient, water content, and soil particle size distribution are mainly collected. These parameters can be obtained through on-site drilling sampling, geophysical exploration, permeability experiments, etc., to ensure the authenticity and effectiveness of the data.

[0021] In a possible implementation, rock density refers to the mass of rock and soil per unit volume. This parameter is usually determined by on-site sampling combined with laboratory experiments, such as measuring using the Archimedes method or the pycnometer method. For heterogeneous strata, the variation of rock density at different depths also needs to be considered, and the data is weighted and averaged to more accurately reflect the geological conditions.

[0022] Specifically, the permeability coefficient reflects the seepage ability of groundwater in rock and soil media. The determination of the permeability coefficient can be carried out by on-site pumping tests or laboratory permeability tests. Generally, in homogeneous soil layers, the calculation of the permeability coefficient can be obtained from Darcy's law:; q = k·A·i; where q is the seepage flow rate; A is the cross-sectional area of seepage; i is the hydraulic gradient; k is the permeability coefficient; In some embodiments, for layered heterogeneous soil layers, the equivalent permeability coefficient method can be used for calculation, where the vertical permeability coefficient k v and the horizontal permeability coefficient k h are calculated respectively in the following ways: where k i is the permeability coefficient of the i-th layer of soil; H i is the thickness of the i-th layer of soil; n is the number of samples.

[0023] As an option, water content represents the ratio of the mass of water in the soil to the mass of dry soil. The determination of water content generally uses the drying method, that is, after drying the soil sampled on-site to a constant weight, the mass difference before and after water evaporation is calculated to determine the water content w: where m w is the mass of water in the soil; m d is the mass of the soil after drying.

[0024] In some embodiments, to improve the accuracy of water content data, on-site real-time monitoring can be combined with the time domain reflectometry (TDR) method or resistivity measurement method.

[0025] In addition, the soil particle size distribution refers to the grading situation of soil particles, and is generally determined by the sieving method or the sedimentation method. Specifically, in coarse-grained soils (such as sand, gravel), the sieving method is used to separate soil particles through sieves with different pore sizes and measure the content of each particle size grade. In fine-grained soils (such as silt, clay), the hydrometer method or laser particle size analysis method can be used to measure the particle size distribution. The soil particle size distribution has an important impact on the uplift performance of anchor rods, so it needs to be measured and statistically analyzed with emphasis.

[0026] In a possible implementation, in order to improve the accuracy of geological data collection, in-situ tests can be adopted. For example, the Standard Penetration Test (SPT) is used to evaluate the compactness of soil layers; the Cone Penetration Test (CPT) measures the shear strength parameters of soil; the seismic wave test method (such as the Rayleigh wave test) is used to determine the elastic modulus of soil mass; the groundwater level monitor monitors the long-term change trend of the groundwater level.

[0027] And the collection of geological data can be combined with remote sensing technologies, such as Ground Penetrating Radar (GPR) or satellite remote sensing imaging, for geological feature extraction in a large area, improving the timeliness and coverage of data collection.

[0028] Therefore, by collecting on-site geological data in various ways, the accuracy and integrity of the input data are ensured, thus providing a reliable basis for subsequent geological feature identification, design parameter optimization, and risk assessment.

[0029] Based on the support vector machine algorithm, learn from the on-site geological data to establish a geological feature identification model; In this embodiment, the learning of on-site geological data is the core link for establishing the geological feature identification model. The accuracy of this model directly affects the evaluation quality of the applicable conditions of the cage-type anti-floating anchor. Therefore, in the data processing and learning process, the diversity of geological data and its impact on the adaptability of the anchor need to be fully considered. By adopting the support vector machine (SVM) algorithm, classifying and extracting features from the collected geological data, an efficient and stable geological feature identification model can be established, thus providing a basis for subsequent design parameter prediction and optimization.

[0030] In this embodiment, the support vector machine algorithm is used to classify and learn key geological data such as rock density, permeability coefficient, water content, and soil particle size distribution, and establish an adaptability determination model. Generally, SVM is suitable for data classification in high-dimensional spaces and can construct an optimal decision boundary between non-linear geological data features to improve the classification accuracy.

[0031] In a possible implementation, first, standardize the collected geological data to eliminate the influence between different data scales. The standardization method can adopt mean normalization or Z-score normalization, and the calculation method of Z-score normalization is as follows: where, X ′ is the standardized data; X is the original data; μ is the mean of the data; σ is the standard deviation of the data.

[0032] As an option, during the geological data preprocessing stage, the principal component analysis (PCA) method can also be used to reduce the dimensionality of the data, so as to reduce redundant information and improve the calculation efficiency. PCA mainly realizes the dimensionality reduction of high-dimensional data by solving the eigenvectors of the covariance matrix, and the calculation formula is as follows: where C is the covariance matrix; X i is the i-th data sample; μ is the total number of samples; (X i -μ) T is the transpose of the decentralized data.

[0033] In some embodiments, SVM uses the radial basis kernel function (RBF-Kernel) for non-linear classification to improve the accuracy of the adaptability determination model. The expression of the radial basis kernel function is as follows: K(x i ,x j )=exp(-γ∥x i -x j ∥ 2 ); where K(x i ,x j ) is the kernel function value between samples x i and x j ; γ is the parameter of the kernel function; ∥x i -x j ∥ 2 is the square of the Euclidean distance; represents the distance between samples x i and x j , which is used to measure the difference or similarity between samples.

[0034] Specifically, the SVM training process finds the optimal hyperplane by solving the following optimization problem to maximize the data classification margin: y i (w·x i +b)≥1; where w is the hyperplane normal vector; b is the bias term; y i is the class label of the sample.

[0035] In a possible implementation, after training, when classifying new geological data, the decision function is adopted: f(x)=sign(w·x+b); If f(x)>0, then this geological condition is applicable to the cage-type anti-floating anchor rod; otherwise, this condition is not applicable.

[0036] As a further optimization method, the cross-validation method can be used to optimize the SVM model to determine the optimal hyperparameters (such as the kernel parameter γ). Generally, K-fold cross-validation can be adopted for cross-validation. The training data set is divided into K parts, which are respectively used for training and testing to evaluate the generalization ability of the model.

[0037] Moreover, to improve the robustness of the geological characteristic recognition model, the ensemble learning method can also be combined, such as the multiple support vector machine (Multiple-SVM) model. That is, multiple SVM models are used to independently train different types of geological features, and the applicability of the anchor rod is comprehensively judged through a voting mechanism. This method can effectively improve the accuracy of applicability determination in complex geological environments.

[0038] Therefore, through the geological characteristic recognition model based on the support vector machine algorithm, the present invention realizes the classification learning of on-site geological data, and combines feature engineering, kernel function optimization and model integration technical means to improve the accuracy and stability of the anchor rod applicability evaluation, providing a data basis for subsequent design parameter prediction and optimization.

[0039] According to the geological characteristic recognition model, the applicability of on-site geological data is evaluated, and application suggestions for the anchor rod are output. In this embodiment, based on the on-site geological data collected in the previous steps, the geological characteristic recognition model can evaluate the applicability of the data, so as to output appropriate application suggestions for the cage-type anti-floating anchor rod. Through this process, the present invention can accurately determine whether the cage-type anti-floating anchor rod is suitable for a specific construction environment in a complex geological environment, thus effectively reducing misjudgment in the design stage and unnecessary cost waste.

[0040] Specifically, the role of the geological characteristic recognition model is to learn and analyze the collected geological data and evaluate the applicability of the cage-type anti-floating anchor rod under different geological characteristics. This model adopts the support vector machine (SVM) algorithm, maps the geological data to a higher-dimensional feature space, and determines the applicability by calculating the similarity between different feature vectors. Specifically, SVM constructs a decision boundary by finding the maximum classification interval to judge whether each geological sample is suitable for the cage-type anti-floating anchor rod.

[0041] Generally, the output of the model is a binary classification result, indicating whether the measured geological conditions meet the use standards of the cage-type anti-floating anchor rod. Through the calculated decision value, it can be judged whether the geological conditions are suitable for using the cage-type anti-floating anchor rod.

[0042] In some embodiments, the support vector machine uses a radial basis kernel function (RBF kernel function) for non - linear classification to improve the accuracy of the model under complex geological conditions. This kernel function helps the model better handle non - linear problems and improve the accuracy of applicability determination by calculating the similarity between samples.

[0043] To further enhance the prediction ability of the model, especially for cases with complex geological features, the present invention can also combine multiple different kernel functions to improve the adaptability of the model. In this way, the support vector machine can more accurately divide applicable and inapplicable geological conditions in the high - dimensional space, further improving the accuracy of the application suggestions for cage - type anti - floating anchor rods.

[0044] In some embodiments, for different geological conditions, such as parameters like rock type, soil density, permeability coefficient, etc., the model can automatically adjust the classification boundary of the support vector machine by learning historical geological data, thereby accurately judging which conditions are suitable for the use of cage - type anti - floating anchor rods. Therefore, the model can not only improve the accuracy of prediction but also reduce design errors caused by human factors.

[0045] In addition, the output of the geological characteristic recognition model is not limited to the applicability judgment. It can also further output specific design suggestions according to the evaluation results. According to the results of the applicability evaluation, the system can automatically suggest a suitable design scheme for the cage - type anti - floating anchor rod. For example, if the geological conditions meet the usage standards, the system can output a suggestion to use a cage - type anti - floating anchor rod with standard length, diameter, and spacing; if not applicable, the system will suggest adopting a different anti - floating design scheme or adjusting the design parameters.

[0046] Therefore, the geological characteristic recognition model based on the support vector machine algorithm can accurately evaluate the applicability of anchor rods in complex geological environments, avoiding the prediction errors of traditional methods in complex environments. Through this evaluation process, the present invention realizes more efficient and accurate application suggestions for cage - type anti - floating anchor rods, significantly improving the safety and economy of engineering design.

[0047] Using a deep neural network, estimate the anchor rod design parameters based on on - site geological data and anchor rod application suggestions; In this embodiment, a deep neural network (DNN) is used to estimate the design parameters of the anchor rod. By learning the relationship between a large amount of historical geological data and the anchor rod design parameters, this model can automatically extract key features from complex geological features and give preliminary design suggestions. The core goal of this process is to convert geological data into preliminary parameters for anchor rod design, thus providing strong support for subsequent optimization and adjustment.

[0048] Specifically, a deep neural network (DNN) is used as the core component of the model, which gradually processes and transforms the input data through multiple layers of neuron nodes. In this model, the input data includes various geological characteristics collected on-site, such as rock density, permeability coefficient, water content, soil particle size distribution, etc. Specifically, the DNN receives these geological data through the input layer, gradually extracts the potential features in the data through several hidden layers, and finally generates the preliminary design parameters of the anchor bolt, such as length, diameter, spacing, etc., in the output layer.

[0049] Generally, the structure of a deep neural network consists of multiple layers of neuron nodes. Each layer performs a weighted sum of the output of the previous layer and undergoes a non-linear transformation through an activation function. Specifically, the output z of a certain layer (l) can be calculated by the following formula: z (l) = W (l) ·a (l-1) + b (l) ; where, W (l) is the weight matrix of the l-th layer; a (l-1) is the activation output of the (l - 1)-th layer; b (l) is the bias vector of the l-th layer.

[0050] Through layer-by-layer calculation, the neural network transforms the input geological data into the preliminary parameters for the anchor bolt design. These parameters are aggregated through the output layer to obtain the preliminary design result of the anchor bolt.

[0051] As an option, the activation function of the deep neural network can be selected as the ReLU (Rectified-Linear-Unit) function, which can effectively solve the problem of gradient vanishing and improve the training efficiency. The calculation formula of ReLU is as follows: a (l) = max(0, z (l) ); where, a (l) is the activation value; through this function, the model can effectively model the non-linear features in the input data.

[0052] In some embodiments, to improve the accuracy and robustness of the model, the training process of the network adopts the backpropagation algorithm, and optimizes the model parameters by minimizing the loss function. The loss function usually adopts methods such as mean square error (MSE) or cross entropy (Cross-Entropy), and the specific selection varies according to the nature of the task and the goal. The expression of the mean square error loss function Z is as follows: where, is the model prediction value; ya is the actual value; n is the number of samples.

[0053] Specifically, in the application of the present invention, the deep neural network can automatically predict the preliminary design parameters of the anchor rod according to the on-site geological data. This process greatly reduces manual participation and can fully consider various complex geological features, laying a solid foundation for subsequent optimization and adjustment. Through multiple trainings and validations, the model continuously optimizes its prediction ability and finally outputs the design parameters that meet the bearing capacity requirements.

[0054] In a possible implementation manner, the present invention can also combine other optimization algorithms, such as the genetic algorithm (GA) or particle swarm optimization (PSO), to further optimize the preliminary design results. Through these optimization algorithms, the model can find the optimal solution within the range of design parameters, thereby effectively reducing costs and improving design efficiency.

[0055] Therefore, through the learning and prediction of on-site geological data by the deep neural network, the present invention can quickly and accurately calculate the preliminary design parameters of the cage-type anti-floating anchor rod, provide strong technical support for subsequent optimization and adjustment, reduce the error of manual intervention at the same time, and improve the accuracy and safety of engineering design.

[0056] The genetic algorithm is used to optimize the design parameters of the anchor rod to obtain the design scheme.

[0057] In this embodiment, the deep neural network (DNN) provides the basic parameters for the preliminary design of the cage-type anti-floating anchor rod. These preliminary design parameters include important design elements such as the length, diameter, and spacing of the anchor rod. In order to further optimize the design and ensure the economy and safety of the design scheme, the genetic algorithm (GA) is used to optimize these preliminary design parameters, thereby obtaining the final optimal design scheme.

[0058] Specifically, the genetic algorithm (GA) optimizes the design parameters by simulating the process of species evolution in nature. The algorithm includes steps such as selection, crossover, mutation, and evaluation, aiming to finally find the optimal parameters that meet all design requirements through continuous iterative optimization. The core idea of the genetic algorithm is to gradually approach the global optimal solution by selecting high-quality individuals and generating a new generation of individuals.

[0059] Specifically, the initial population of the genetic algorithm consists of the preliminary design parameters generated by the deep neural network. Each individual represents a potential design scheme, including parameters such as the length, diameter, and spacing of the anchor rod. Generally, the selection operation is completed by calculating the fitness of each individual. The fitness f opt (L, D, S) is calculated by the following objective function: f opt (L, D, S) = α·C mat(L, D, S) + β·C labor (L, D, S) - θ·Strength(L, D, S); Wherein, L represents the length of the bolt; D represents the diameter of the bolt; S represents the bolt spacing; C mat is the material consumption cost; C labor is the labor cost; Strength represents the bearing capacity of the bolt; α, β, θ are weight coefficients used to control the relative importance between different objectives.

[0060] And during the selection process, individuals with higher fitness are preferentially selected to generate the next generation of individuals. Next, new design solutions are generated through the crossover operation. These new design solutions inherit some excellent characteristics of the parent individuals and introduce a certain degree of randomness through the mutation operation to increase the diversity of the solution space and prevent the algorithm from falling into a local optimal solution.

[0061] Meanwhile, the crossover operation usually adopts single-point crossover or multi-point crossover. Specifically, one possible implementation is to divide the design parameters of the parent into two parts and exchange information at the crossover point to generate a new offspring design solution. The mutation operation is to make a small random modification to a certain part of the design parameters to increase the breadth of the search space. The probability and range of mutation are usually controlled in the algorithm parameters to ensure that the algorithm does not converge prematurely to an unsatisfactory solution.

[0062] For each generation of individuals, by evaluating their fitness function, the algorithm will select the optimal design solution as the basis for the next generation. As the number of iterations increases, high-quality design solutions will gradually dominate and finally converge to the optimal solution. The final optimal design solution will meet all the constraint conditions, including requirements in multiple aspects such as bearing capacity, safety, and economy.

[0063] In some embodiments of the present invention, in order to improve the efficiency and accuracy of the genetic algorithm, a local search algorithm may be combined to refine the optimal solution. The local search algorithm can further optimize the accuracy of the solution on the basis of the genetic algorithm. For example, a simulated annealing algorithm or a particle swarm optimization algorithm is used to refine the results of the genetic algorithm to ensure the final optimization of the design solution.

[0064] Specifically, the optimization process of the genetic algorithm combines the geological characteristic identification model and the preliminary design parameters estimated by the deep neural network, making the optimization more in line with the actual working conditions. Through this multi-level and multi-step optimization mechanism, the present invention can further reduce the material consumption and project cost, improve the design efficiency, and reduce unnecessary waste while ensuring that the bolt design meets the bearing capacity requirements.

[0065] Therefore, by combining a deep neural network and a genetic algorithm, the efficient optimization of the design parameters of the cage - type anti - floating anchor rod is achieved. In this process, the genetic algorithm effectively improves the accuracy and economy of the design scheme, ensuring the safety and cost - effectiveness of the engineering project. At the same time, this optimization process is automated, reducing manual intervention and improving the reliability and efficiency of the design.

[0066] Embodiment 2: Please refer to the attached Figure 2 , this embodiment provides a determination system for the applicable conditions of a cage - type anti - floating anchor rod, including: A data acquisition module for collecting on - site geological data; A geological characteristic identification module that classifies the on - site geological data based on the support vector machine algorithm and outputs application suggestions for the cage - type anti - floating anchor rod; A design parameter optimization module that combines a deep neural network and a genetic algorithm to optimize the anchor rod design parameters in the application suggestions; A risk assessment module that, based on the anchor rod design parameters optimized by the design parameter optimization module, uses the probabilistic risk assessment method to generate a risk probability map and adjust the design redundancy; A user interaction module for providing an interaction interface to display the design scheme and the anchor rod design parameters in real - time.

[0067] In this embodiment, for the on - site geological data collected in each operation, by introducing a storage module, all historical data can be saved and managed, and an efficient geological condition evaluation system is established. By introducing the storage module, not only can the geological data of each project be effectively archived, but also the design efficiency and accuracy can be improved through data reuse and comparison with historical data in subsequent projects.

[0068] Specifically, the main function of the storage module is to record the geological data of each engineering project in real - time and store it together with the corresponding design scheme and optimization results. Specifically, all on - site measured geological data, including information such as rock density, permeability coefficient, water content, and soil particle size distribution, will be saved in a database. Each data record will be associated with the project number, geological characteristics, anchor rod design parameters, etc., ensuring that the data can be clearly traced and managed between projects.

[0069] Generally, the storage module uses a relational database (such as MySQL, PostgreSQL, etc.) or a non - relational database (such as MongoDB, NoSQL, etc.) for data storage and management. Through the table structure design in the database, the geological data is associated with the project details. For example, the table structure in the database may include the following fields: Project number: uniquely identifies each engineering project; Geological data: rock density, permeability coefficient, water content, soil particle size distribution, etc.; Design parameters: including preliminary design data such as the length, diameter, and spacing of the anchor rods; Optimization results: the final design scheme optimized by the genetic algorithm; Risk assessment results: risk maps and suggestions for adjusting design redundancy based on the probabilistic risk assessment method.

[0070] As an option, to improve the query and data processing efficiency of the storage module, historical data can also be indexed and classified. Through the classified indexing of different project categories and geological conditions, users can quickly find historical cases with similar geological conditions to the new project when encountering a new project, thus providing reference and basis for the design scheme of the new project.

[0071] In a possible implementation, the system can quickly retrieve the matching historical geological data and its corresponding cage-type anti-floating anchor rod design scheme from the storage module according to the on-site measured geological data input for the new engineering project. In this way, the design of the new project can not only be customized according to the current on-site data, but also combined with the successful design schemes and optimization results in the historical data to improve the accuracy and efficiency of the design. For example, if the geological conditions of a new engineering project are highly similar to those of a previous project, the system can quickly extract the historical data of that project and provide a preliminary design scheme based on this data.

[0072] Specifically, the system first standardizes and normalizes the geological data collected on-site through the data preprocessing module to ensure consistent data formats. Then, it uses a geological feature recognition model based on support vector machine (SVM) for applicability assessment to determine whether the geological conditions are suitable for cage-type anti-floating anchor rods. If applicable, the system will provide the most matching design parameters in history based on the stored data and make a preliminary parameter estimation for the anchor rod design in combination with a deep neural network (DNN). Finally, the storage module will extract the optimization scheme of the historical project as a reference and optimize the design of the new project.

[0073] As a further technical extension, the storage module can also integrate machine learning and artificial intelligence technologies to gradually "learn" the design optimization experience in each engineering project and feedback it into the model for continuous improvement. For example, the system can automatically track the feedback of historical projects, collect the effect data after project implementation, and re-evaluate and optimize the design scheme. Through the continuous learning process, the accuracy of the design scheme can be continuously improved and the project risk can be further reduced.

[0074] Therefore, by adding a storage module, the present invention not only realizes an efficient geological condition evaluation system, but also can accumulate and reuse historical project data, further improving the design efficiency and accuracy, and reducing the design cost and risk. In a new project, only the geological data measured on site needs to be input, and the system can quickly output appropriate application suggestions for cage anti-floating anchor rods, making the engineering design process more intelligent and automated.

[0075] Although the embodiments of the present invention have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A determination method for the applicable conditions of cage anti-floating anchor rods, characterized in that It includes the following steps: Collect on-site geological data; Based on the support vector machine algorithm, learn the on-site geological data and establish a geological characteristic identification model; According to the geological characteristic identification model, conduct an applicability assessment on the on-site geological data and output anchor bolt application suggestions; Using a deep neural network, estimate the anchor bolt design parameters based on the on-site geological data and anchor bolt application suggestions; Adopt a genetic algorithm to optimize the anchor bolt design parameters and obtain a design scheme.

2. The determination method for applicable conditions of a cage-shaped anti-floating anchor rod according to claim 1, characterized in that, The on-site geological data includes rock density, permeability coefficient, water content, and soil particle size distribution.

3. A determination method for the applicable conditions of a cage-shaped anti-floating anchor rod according to claim 1, characterized in that, The deep neural network includes an input layer, a hidden layer, and an output layer. The input layer is used to receive on-site geological data, and the output layer is used to estimate the anchor bolt design parameters.

4. The determination method for the applicable conditions of a cage anti-floating anchor rod according to claim 3, characterized in that, The anchor bolt design parameters include the length, diameter, and spacing of the anchor bolt.

5. A method for determining the applicable conditions of a cage anti-floating anchor rod according to claim 1, characterized in that The genetic algorithm is based on the anchor bolt design parameters and optimizes the anchor bolt design parameters by simulating the natural evolution process.

6. A determination method for the applicable conditions of a cage anti-floating anchor rod according to claim 5, characterized in that, The natural evolution process includes: Selection: Select design parameters with high fitness values as parents; Crossover: Combine the parent design parameters through crossover to form new offspring design parameters and generate several design candidate schemes; Mutation: Mutate several design candidate schemes of the offspring. The mutation includes randomly changing the design parameters; Evaluation: Calculate the fitness values of all design candidate schemes after mutation and determine whether the design candidate schemes meet the design objectives according to the fitness values; Termination condition: When the design candidate scheme meets the requirements, terminate the evolution process and output the design candidate scheme as the optimal design scheme.

7. A determination method for the applicable conditions of a cage-type anti-floating anchor rod according to claim 1, characterized in that, The deep neural network further includes a probabilistic risk assessment for generating a risk assessment report based on seismic loads, groundwater level fluctuations, and seasonal temperature changes.

8. A determination system for the applicable conditions of a cage-type anti-floating anchor rod, based on the method for determining the applicable conditions of a cage-type anti-floating anchor rod according to any one of claims 1-7, characterized in that, It includes: A data acquisition module for collecting on-site geological data; A geological characteristic identification module for classifying on-site geological data based on the support vector machine algorithm and outputting anchor bolt application suggestions; A design parameter optimization module for optimizing the anchor bolt design parameters in the anchor bolt application suggestions by combining a deep neural network and a genetic algorithm; A risk assessment module for generating a risk probability map and adjusting the design redundancy using a probabilistic risk assessment method based on the anchor bolt design parameters optimized by the design parameter optimization module; A user interaction module for providing an interaction interface and displaying the design scheme and anchor bolt design parameters in real time.

Images